Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The doorbell rang, shattering the otherwise peaceful Saturday morning. Sarah scrambled to open the door, only to find her niece, Olivia, clutching a crayon-covered drawing in her tiny hand. "Look, Auntie Sarah!" Olivia declared, her face beaming. The drawing was an elaborate depiction of a castle, but what caught Sarah's attention was the tiny, winged figure perched atop one of the turrets. It was "Pip," her imaginary friend.

Sarah bent down, her heart thumping a little too fast, and ruffled Olivia’s hair. “Wow, that’s amazing, sweetie!” she exclaimed.

Immediately, she grabbed a thick black marker and started drawing a dragon swooping down to protect the castle. Olivia joined in and yelled, “He needs some armor!”

Emotion: playful

Cluster: Positive / Joy
PC1 (Valence): 4.42 Positive
PC2 (Disposition): 1.44

Role in Research

This story is one of 1,000 stories generated for the emotion playful. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 playful stories, after denoising with neutral dialogue baselines, produces the playful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the playful vector is projected through the unembedding matrix.

Promoted:
B0.662
(!)0.566
!0.562
!?0.553
😜0.553
Suppressed:
ness-0.685
😞-0.590
S-0.562
😔-0.470
идти-0.461